{
  "id": "LK-SP-HIN-003",
  "slug": "hindi-speech-recognition-utterances",
  "title": "Hindi speech recognition utterances",
  "modality": "speech",
  "speechType": "conversational",
  "kind": "asr",
  "unit": "utterances",
  "collection": "mixed",
  "language": {
    "name": "Hindi",
    "native": "हिन्दी",
    "iso": "hin",
    "bcp47": "hi-IN",
    "script": "Devanagari"
  },
  "languages": [
    {
      "name": "Hindi",
      "native": "हिन्दी",
      "iso": "hin",
      "bcp47": "hi-IN",
      "script": "Devanagari"
    }
  ],
  "region": "India",
  "domain": "insurance calls, general conversation",
  "scripted": null,
  "parties": null,
  "hours": 350.3,
  "transcribed": true,
  "channels": "mono",
  "source": "Recorded for the dataset",
  "review": "Every recording has a complete, segment-level transcript",
  "personalData": "Redacted",
  "licence": "Custom",
  "sheetRows": [
    5,
    14
  ],
  "sample": null,
  "gaps": [],
  "bundleId": "asr-hi",
  "relatedSlugs": [
    "hindi-call-centre-insurance",
    "hindi-general-conversation"
  ],
  "measured": {
    "id": "asr-hi",
    "files": 218428,
    "conversations": 2104,
    "utterances": 218428,
    "turns": null,
    "speakers": 667,
    "speakerGender": {
      "female": 325,
      "male": 330
    },
    "channels": null,
    "transcripts": 0,
    "segments": 218428,
    "words": 3377105,
    "bandwidth": null,
    "bandwidthCounts": null,
    "telephoneBandFiles": null,
    "snrMedianDb": null,
    "container": "flac",
    "sampleRateHz": 16000,
    "bitDepth": 16,
    "pii": "Numbers of 4 or more digits, digit strings spoken as words, and email addresses are masked as [pii] in text and replaced by a tone in audio. First names are not masked.",
    "release": "v1.0",
    "updatedAt": "2026-09-29T00:21",
    "profile": null,
    "provisional": false
  },
  "utterances": {
    "measured": 142,
    "distinctSpeakers": 111,
    "genders": {
      "female": 59,
      "male": 81
    },
    "quality": {
      "snrDb": 43.5,
      "bandwidthHz": 8000,
      "label": "some background"
    },
    "clips": [
      {
        "id": "hindi-speech-recognition-utterances--u1",
        "sourceId": "utt-8b04744a2e",
        "text": "thank you so much ma'am phone करने के लिए धन्यवाद",
        "durationS": 3.14,
        "gender": "female",
        "speakerId": "hi-cc-insurance-s0119",
        "snrDb": 92.4,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u1.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 23788,
          "sha256": "5eff95a5565ce9ad5793005f8063387ca96e238be7ef7d155ca63a713881dea2"
        }
      },
      {
        "id": "hindi-speech-recognition-utterances--u2",
        "sourceId": "utt-c5e37123a2",
        "text": "हाँ! हाँ-हाँ",
        "durationS": 2.82,
        "gender": "female",
        "speakerId": "hi-cc-insurance-s0189",
        "snrDb": 85.5,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u2.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 16285,
          "sha256": "63a99ff1a19685d2c904370415df50f11647ca14d4af622b0cd5900f03cac705"
        }
      },
      {
        "id": "hindi-speech-recognition-utterances--u3",
        "sourceId": "utt-eac01ceceb",
        "text": "तो आप्ता के वजह से तो इतनी सारी आफत पड़ती हैं की सब जनता परेशान है.",
        "durationS": 6.96,
        "gender": "male",
        "speakerId": "hi-cc-insurance-s0165",
        "snrDb": 72.7,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u3.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 60066,
          "sha256": "88fc9fbbccbf66341f890de3e74740259c0ea2e6e80fbee2cec5e48f0f181d6f"
        }
      },
      {
        "id": "hindi-speech-recognition-utterances--u4",
        "sourceId": "utt-9d209982b4",
        "text": "आपकी गाड़ी जो हैं उसको amount मिलेगा आपका जो भी गाड़ी पे नुकसान आ रहा हैं ठीक हैं उसके ऊपर आपको insurance मिलेगा आपको कुछ होता हैं तो आपका insurance नहीं मिलेगा.",
        "durationS": 11.55,
        "gender": "male",
        "speakerId": "hi-cc-insurance-s0227",
        "snrDb": 71.6,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u4.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 104069,
          "sha256": "940b2e5b74481f8a1eb025c9e01b6c282ae9a28d0becfde3d6138bc0e2cce20b"
        }
      },
      {
        "id": "hindi-speech-recognition-utterances--u5",
        "sourceId": "utt-1cda487664",
        "text": "आपको दस अंकों वाला बताना है ma'am",
        "durationS": 3.06,
        "gender": "male",
        "speakerId": "hi-cc-insurance-s0328",
        "snrDb": 67.8,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u5.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 28865,
          "sha256": "9653205831e29bc22526990127b4e191a68fd125776a608e67400d28ff8dda04"
        }
      },
      {
        "id": "hindi-speech-recognition-utterances--u6",
        "sourceId": "utt-3183474dab",
        "text": "ma'am उनका नाम अजित होंगा. नंबर मे आपको नहीं दे सकता ma'am.",
        "durationS": 3.3,
        "gender": "male",
        "speakerId": "hi-cc-insurance-s0330",
        "snrDb": 66.7,
        "audio": {
          "url": "/lokah-samples/hindi-speech-recognition-utterances--u6.m4a",
          "encodingFormat": "audio/mp4",
          "bytes": 32144,
          "sha256": "89fe3e4cbe6f7819ce4a84ff20c8b7eccd9730666a3468945f756d39953f7754"
        }
      }
    ]
  },
  "url": "https://kenpathlabs.com/lokah/datasets/hindi-speech-recognition-utterances"
}